A GENERALIZATION OF POLYAK CONVERGENCE RESULT FOR SUBGRADIENT OPTIMIZATION
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
This paper generalizes a practical convergence result first presented by Polyak. This new result presents a theoretical justification for the step size which has been successfully used in several specialized algorithms which incorporate the subgradient optimization approach. 1987 The Mathematical Programming Society, Inc.